July 30, 2019

2913 words 14 mins read

Paper Group AWR 51

EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies. An Unsupervised Method for Estimating the Global Horizontal Irradiance from Photovoltaic Power Measurements. Classification and clustering for observations of event time data using non-homogeneous Poisson process models. SkipFlow: Incorporating Neural Coherence Features …

EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies


Title	EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies
Authors	Redouane Lguensat, Miao Sun, Ronan Fablet, Evan Mason, Pierre Tandeo, Ge Chen
Abstract	This work presents EddyNet, a deep learning based architecture for automated eddy detection and classification from Sea Surface Height (SSH) maps provided by the Copernicus Marine and Environment Monitoring Service (CMEMS). EddyNet is a U-Net like network that consists of a convolutional encoder-decoder followed by a pixel-wise classification layer. The output is a map with the same size of the input where pixels have the following labels {‘0’: Non eddy, ‘1’: anticyclonic eddy, ‘2’: cyclonic eddy}. We investigate the use of SELU activation function instead of the classical ReLU+BN and we use an overlap based loss function instead of the cross entropy loss. Keras Python code, the training datasets and EddyNet weights files are open-source and freely available on https://github.com/redouanelg/EddyNet.
Tasks	Oceanic Eddy Classification
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03954v1
PDF	http://arxiv.org/pdf/1711.03954v1.pdf
PWC	https://paperswithcode.com/paper/eddynet-a-deep-neural-network-for-pixel-wise
Repo	https://github.com/redouanelg/EddyNet
Framework	none

An Unsupervised Method for Estimating the Global Horizontal Irradiance from Photovoltaic Power Measurements


Title	An Unsupervised Method for Estimating the Global Horizontal Irradiance from Photovoltaic Power Measurements
Authors	Lorenzo Nespoli, Vasco Medici
Abstract	In this paper, we present a method to determine the global horizontal irradiance (GHI) from the power measurements of one or more PV systems, located in the same neighborhood. The method is completely unsupervised and is based on a physical model of a PV plant. The precise assessment of solar irradiance is pivotal for the forecast of the electric power generated by photovoltaic (PV) plants. However, on-ground measurements are expensive and are generally not performed for small and medium-sized PV plants. Satellite-based services represent a valid alternative to on site measurements, but their space-time resolution is limited. Results from two case studies located in Switzerland are presented. The performance of the proposed method at assessing GHI is compared with that of free and commercial satellite services. Our results show that the presented method is generally better than satellite-based services, especially at high temporal resolutions.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06878v3
PDF	http://arxiv.org/pdf/1706.06878v3.pdf
PWC	https://paperswithcode.com/paper/an-unsupervised-method-for-estimating-the
Repo	https://github.com/supsi-dacd-isaac/GHIEstimator
Framework	none

Classification and clustering for observations of event time data using non-homogeneous Poisson process models


Title	Classification and clustering for observations of event time data using non-homogeneous Poisson process models
Authors	Duncan Barrack, Simon Preston
Abstract	Data of the form of event times arise in various applications. A simple model for such data is a non-homogeneous Poisson process (NHPP) which is specified by a rate function that depends on time. We consider the problem of having access to multiple independent observations of event time data, observed on a common interval, from which we wish to classify or cluster the observations according to their rate functions. Each rate function is unknown but assumed to belong to a finite number of rate functions each defining a distinct class. We model the rate functions using a spline basis expansion, the coefficients of which need to be estimated from data. The classification approach consists of using training data for which the class membership is known, to calculate maximum likelihood estimates of the coefficients for each group, then assigning test observations to a group by a maximum likelihood criterion. For clustering, by analogy to the Gaussian mixture model approach for Euclidean data, we consider mixtures of NHPP and use the expectation-maximisation algorithm to estimate the coefficients of the rate functions for the component models and group membership probabilities for each observation. The classification and clustering approaches perform well on both synthetic and real-world data sets. Code associated with this paper is available at https://github.com/duncan-barrack/NHPP .
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.02111v4
PDF	http://arxiv.org/pdf/1703.02111v4.pdf
PWC	https://paperswithcode.com/paper/classification-and-clustering-for
Repo	https://github.com/duncan-barrack/NHPP
Framework	none

SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring


Title	SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring
Authors	Yi Tay, Minh C. Phan, Luu Anh Tuan, Siu Cheung Hui
Abstract	Deep learning has demonstrated tremendous potential for Automatic Text Scoring (ATS) tasks. In this paper, we describe a new neural architecture that enhances vanilla neural network models with auxiliary neural coherence features. Our new method proposes a new \textsc{SkipFlow} mechanism that models relationships between snapshots of the hidden representations of a long short-term memory (LSTM) network as it reads. Subsequently, the semantic relationships between multiple snapshots are used as auxiliary features for prediction. This has two main benefits. Firstly, essays are typically long sequences and therefore the memorization capability of the LSTM network may be insufficient. Implicit access to multiple snapshots can alleviate this problem by acting as a protection against vanishing gradients. The parameters of the \textsc{SkipFlow} mechanism also acts as an auxiliary memory. Secondly, modeling relationships between multiple positions allows our model to learn features that represent and approximate textual coherence. In our model, we call this \textit{neural coherence} features. Overall, we present a unified deep learning architecture that generates neural coherence features as it reads in an end-to-end fashion. Our approach demonstrates state-of-the-art performance on the benchmark ASAP dataset, outperforming not only feature engineering baselines but also other deep learning models.
Tasks	Feature Engineering
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04981v1
PDF	http://arxiv.org/pdf/1711.04981v1.pdf
PWC	https://paperswithcode.com/paper/skipflow-incorporating-neural-coherence
Repo	https://github.com/SharonVarghese93/MAJORPROJ-IRE
Framework	none

Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection


Title	Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
Authors	Xiaodan Liang, Lisa Lee, Eric P. Xing
Abstract	Despite progress in visual perception tasks such as image classification and detection, computers still struggle to understand the interdependency of objects in the scene as a whole, e.g., relations between objects or their attributes. Existing methods often ignore global context cues capturing the interactions among different object instances, and can only recognize a handful of types by exhaustively training individual detectors for all possible relationships. To capture such global interdependency, we propose a deep Variation-structured Reinforcement Learning (VRL) framework to sequentially discover object relationships and attributes in the whole image. First, a directed semantic action graph is built using language priors to provide a rich and compact representation of semantic correlations between object categories, predicates, and attributes. Next, we use a variation-structured traversal over the action graph to construct a small, adaptive action set for each step based on the current state and historical actions. In particular, an ambiguity-aware object mining scheme is used to resolve semantic ambiguity among object categories that the object detector fails to distinguish. We then make sequential predictions using a deep RL framework, incorporating global context cues and semantic embeddings of previously extracted phrases in the state vector. Our experiments on the Visual Relationship Detection (VRD) dataset and the large-scale Visual Genome dataset validate the superiority of VRL, which can achieve significantly better detection results on datasets involving thousands of relationship and attribute types. We also demonstrate that VRL is able to predict unseen types embedded in our action graph by learning correlations on shared graph nodes.
Tasks	Image Classification
Published	2017-03-08
URL	http://arxiv.org/abs/1703.03054v1
PDF	http://arxiv.org/pdf/1703.03054v1.pdf
PWC	https://paperswithcode.com/paper/deep-variation-structured-reinforcement
Repo	https://github.com/nexusapoorvacus/DeepVariationStructuredRL
Framework	pytorch

Understanding Abuse: A Typology of Abusive Language Detection Subtasks


Title	Understanding Abuse: A Typology of Abusive Language Detection Subtasks
Authors	Zeerak Waseem, Thomas Davidson, Dana Warmsley, Ingmar Weber
Abstract	As the body of research on abusive language detection and analysis grows, there is a need for critical consideration of the relationships between different subtasks that have been grouped under this label. Based on work on hate speech, cyberbullying, and online abuse we propose a typology that captures central similarities and differences between subtasks and we discuss its implications for data annotation and feature construction. We emphasize the practical actions that can be taken by researchers to best approach their abusive language detection subtask of interest.
Tasks
Published	2017-05-28
URL	http://arxiv.org/abs/1705.09899v2
PDF	http://arxiv.org/pdf/1705.09899v2.pdf
PWC	https://paperswithcode.com/paper/understanding-abuse-a-typology-of-abusive
Repo	https://github.com/t-davidson/hate-speech-and-offensive-language
Framework	none

Visualizing the Loss Landscape of Neural Nets


Title	Visualizing the Loss Landscape of Neural Nets
Authors	Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein
Abstract	Neural network training relies on our ability to find “good” minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effects on the underlying loss landscape, are not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a range of visualization methods. First, we introduce a simple “filter normalization” method that helps us visualize loss function curvature and make meaningful side-by-side comparisons between loss functions. Then, using a variety of visualizations, we explore how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.
Tasks
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09913v3
PDF	http://arxiv.org/pdf/1712.09913v3.pdf
PWC	https://paperswithcode.com/paper/visualizing-the-loss-landscape-of-neural-nets
Repo	https://github.com/tomgoldstein/loss-landscape
Framework	pytorch

PELESent: Cross-domain polarity classification using distant supervision


Title	PELESent: Cross-domain polarity classification using distant supervision
Authors	Edilson A. Corrêa Jr, Vanessa Q. Marinho, Leandro B. dos Santos, Thales F. C. Bertaglia, Marcos V. Treviso, Henrico B. Brum
Abstract	The enormous amount of texts published daily by Internet users has fostered the development of methods to analyze this content in several natural language processing areas, such as sentiment analysis. The main goal of this task is to classify the polarity of a message. Even though many approaches have been proposed for sentiment analysis, some of the most successful ones rely on the availability of large annotated corpus, which is an expensive and time-consuming process. In recent years, distant supervision has been used to obtain larger datasets. So, inspired by these techniques, in this paper we extend such approaches to incorporate popular graphic symbols used in electronic messages, the emojis, in order to create a large sentiment corpus for Portuguese. Trained on almost one million tweets, several models were tested in both same domain and cross-domain corpora. Our methods obtained very competitive results in five annotated corpora from mixed domains (Twitter and product reviews), which proves the domain-independent property of such approach. In addition, our results suggest that the combination of emoticons and emojis is able to properly capture the sentiment of a message.
Tasks	Sentiment Analysis
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02657v1
PDF	http://arxiv.org/pdf/1707.02657v1.pdf
PWC	https://paperswithcode.com/paper/pelesent-cross-domain-polarity-classification
Repo	https://github.com/edilsonacjr/pelesent
Framework	tf

Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems


Title	Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems
Authors	Lyudmila Grigoryeva, Juan-Pablo Ortega
Abstract	A new class of non-homogeneous state-affine systems is introduced for use in reservoir computing. Sufficient conditions are identified that guarantee first, that the associated reservoir computers with linear readouts are causal, time-invariant, and satisfy the fading memory property and second, that a subset of this class is universal in the category of fading memory filters with stochastic almost surely uniformly bounded inputs. This means that any discrete-time filter that satisfies the fading memory property with random inputs of that type can be uniformly approximated by elements in the non-homogeneous state-affine family.
Tasks
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00754v3
PDF	http://arxiv.org/pdf/1712.00754v3.pdf
PWC	https://paperswithcode.com/paper/universal-discrete-time-reservoir-computers
Repo	https://github.com/lucasburger/pyRC
Framework	none

Deconvolutional Paragraph Representation Learning


Title	Deconvolutional Paragraph Representation Learning
Authors	Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao, Lawrence Carin
Abstract	Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building block for many applications. We show empirically that compared to RNNs, our framework is better at reconstructing and correcting long paragraphs. Quantitative evaluation on semi-supervised text classification and summarization tasks demonstrate the potential for better utilization of long unlabeled text data.
Tasks	Representation Learning, Text Classification
Published	2017-08-16
URL	http://arxiv.org/abs/1708.04729v3
PDF	http://arxiv.org/pdf/1708.04729v3.pdf
PWC	https://paperswithcode.com/paper/deconvolutional-paragraph-representation
Repo	https://github.com/dreasysnail/textCNN_public
Framework	tf

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices


Title	ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Authors	Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun
Abstract	We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.
Tasks	Image Classification, Object Detection
Published	2017-07-04
URL	http://arxiv.org/abs/1707.01083v2
PDF	http://arxiv.org/pdf/1707.01083v2.pdf
PWC	https://paperswithcode.com/paper/shufflenet-an-extremely-efficient
Repo	https://github.com/afzalahmad0203/tf_shufflenet
Framework	tf

Quadratic Unconstrained Binary Optimization Problem Preprocessing: Theory and Empirical Analysis


Title	Quadratic Unconstrained Binary Optimization Problem Preprocessing: Theory and Empirical Analysis
Authors	Mark Lewis, Fred Glover
Abstract	The Quadratic Unconstrained Binary Optimization problem (QUBO) has become a unifying model for representing a wide range of combinatorial optimization problems, and for linking a variety of disciplines that face these problems. A new class of quantum annealing computer that maps QUBO onto a physical qubit network structure with specific size and edge density restrictions is generating a growing interest in ways to transform the underlying QUBO structure into an equivalent graph having fewer nodes and edges. In this paper we present rules for reducing the size of the QUBO matrix by identifying variables whose value at optimality can be predetermined. We verify that the reductions improve both solution quality and time to solution and, in the case of metaheuristic methods where optimal solutions cannot be guaranteed, the quality of solutions obtained within reasonable time limits. We discuss the general QUBO structural characteristics that can take advantage of these reduction techniques and perform careful experimental design and analysis to identify and quantify the specific characteristics most affecting reduction. The rules make it possible to dramatically improve solution times on a new set of problems using both the exact Cplex solver and a tabu search metaheuristic.
Tasks	Combinatorial Optimization
Published	2017-05-27
URL	http://arxiv.org/abs/1705.09844v1
PDF	http://arxiv.org/pdf/1705.09844v1.pdf
PWC	https://paperswithcode.com/paper/quadratic-unconstrained-binary-optimization
Repo	https://github.com/Brendan-Reid1991/CFD-Algorithms
Framework	none

Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting


Title	Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting
Authors	Ruwan Tennakoon, Alireza Sadri, Reza Hoseinnezhad, Alireza Bab-Hadiashar
Abstract	Identifying the underlying models in a set of data points contaminated by noise and outliers, leads to a highly complex multi-model fitting problem. This problem can be posed as a clustering problem by the projection of higher order affinities between data points into a graph, which can then be clustered using spectral clustering. Calculating all possible higher order affinities is computationally expensive. Hence in most cases only a subset is used. In this paper, we propose an effective sampling method to obtain a highly accurate approximation of the full graph required to solve multi-structural model fitting problems in computer vision. The proposed method is based on the observation that the usefulness of a graph for segmentation improves as the distribution of hypotheses (used to build the graph) approaches the distribution of actual parameters for the given data. In this paper, we approximate this actual parameter distribution using a k-th order statistics based cost function and the samples are generated using a greedy algorithm coupled with a data sub-sampling strategy. The experimental analysis shows that the proposed method is both accurate and computationally efficient compared to the state-of-the-art robust multi-model fitting techniques. The code is publicly available from https://github.com/RuwanT/model-fitting-cbs.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09437v1
PDF	http://arxiv.org/pdf/1705.09437v1.pdf
PWC	https://paperswithcode.com/paper/effective-sampling-fast-segmentation-using
Repo	https://github.com/RuwanT/model-fitting-cbs
Framework	none

Kernel Conditional Exponential Family


Title	Kernel Conditional Exponential Family
Authors	Michael Arbel, Arthur Gretton
Abstract	A nonparametric family of conditional distributions is introduced, which generalizes conditional exponential families using functional parameters in a suitable RKHS. An algorithm is provided for learning the generalized natural parameter, and consistency of the estimator is established in the well specified case. In experiments, the new method generally outperforms a competing approach with consistency guarantees, and is competitive with a deep conditional density model on datasets that exhibit abrupt transitions and heteroscedasticity.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05363v2
PDF	http://arxiv.org/pdf/1711.05363v2.pdf
PWC	https://paperswithcode.com/paper/kernel-conditional-exponential-family
Repo	https://github.com/MichaelArbel/KCEF
Framework	none

Representation Learning for Grounded Spatial Reasoning


Title	Representation Learning for Grounded Spatial Reasoning
Authors	Michael Janner, Karthik Narasimhan, Regina Barzilay
Abstract	The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive rewards. The proposed model learns a representation of the world steered by instruction text. This design allows for precise alignment of local neighborhoods with corresponding verbalizations, while also handling global references in the instructions. We train our model with reinforcement learning using a variant of generalized value iteration. The model outperforms state-of-the-art approaches on several metrics, yielding a 45% reduction in goal localization error.
Tasks	Representation Learning
Published	2017-07-13
URL	http://arxiv.org/abs/1707.03938v2
PDF	http://arxiv.org/pdf/1707.03938v2.pdf
PWC	https://paperswithcode.com/paper/representation-learning-for-grounded-spatial
Repo	https://github.com/JannerM/spatial-reasoning
Framework	pytorch